update agents to compute filtered phase diagram, upgrade submission e…

…rror handling

camd/agent/stability.py

@@ -20,6 +20,8 @@
 from qmpy.analysis.thermodynamics.phase import Phase, PhaseData
 from camd.analysis import PhaseSpaceAL, ELEMENTS
 from camd.agent.base import HypothesisAgent, QBC
+from camd.utils.data import filter_dataframe_by_composition
+from pymatgen import Composition
 
 from sklearn.gaussian_process.kernels import RBF, ConstantKernel
 from sklearn.gaussian_process import GaussianProcessRegressor
@@ -74,22 +76,34 @@ def __init__(
         # These might be able to go into the base class
         self.cv_score = np.nan
 
-    def get_pd(self):
+    def get_pd(self, chemsys=None):
         """
         Refresh the phase diagram associated with the seed_data
 
+        Args:
+            chemsys (str): chemical system for which to filter
+                seed data to provide partial phase diagram
+
         Returns:
             None
         """
         self.pd = PhaseData()
+        # Filter seed data by relevant chemsys
+        if chemsys:
+            total_comp = Composition(chemsys.replace('-', ''))
+            filtered = filter_dataframe_by_composition(
+                self.seed_data, total_comp)
+        else:
+            filtered = self.seed_data
+
         phases = [
             Phase(
                 row["Composition"],
                 energy=row["delta_e"],
                 per_atom=True,
                 description=row_index,
             )
-            for row_index, row in self.seed_data.iterrows()
+            for row_index, row in filtered.iterrows()
         ]
         phases.extend([Phase(el, 0.0, per_atom=True) for el in ELEMENTS])
         self.pd.add_phases(phases)
@@ -174,8 +188,9 @@ def update_candidate_stabilities(self, formation_energies, sort=True, floor=-6.0
             for m_id, data in self.candidate_data.iterrows()
         ]
 
-        # Refresh and copy seed PD
-        pd_ml = deepcopy(self.get_pd())
+        # Refresh and copy seed PD filtered by candidates
+        all_comp = self.candidate_data['Composition'].sum()
+        pd_ml = deepcopy(self.get_pd(all_comp))
         pd_ml.add_phases(candidate_phases)
         space_ml = PhaseSpaceAL(bounds=ELEMENTS, data=pd_ml)
 

camd/experiment/dft.py

@@ -212,7 +212,8 @@ def submit_dft_calcs_to_mc1(self):
             )
 
         for structure_id, row in self.current_data.iterrows():
-            calc_path = os.path.join(parent_dir, structure_id, "_1")
+            # Replace structure id in path to avoid confusing mc1
+            calc_path = os.path.join(parent_dir, structure_id.replace('-', ''), "_1")
             os.makedirs(calc_path)
             with cd(calc_path):
                 # Write input cif file and python model file
@@ -237,21 +238,25 @@ def submit_dft_calcs_to_mc1(self):
                             "us-east-1",
                         ]
                     )
+                    response = response.decode("utf-8")
+                    response = re.findall("({.+})", response, re.DOTALL)[0]
+                    data = json.loads(response)
+                    data.update(
+                        {
+                            "path": os.getcwd(),
+                            "status": "SUBMITTED",
+                            "start_time": datetime.utcnow(),
+                        }
+                    )
                 except subprocess.CalledProcessError as e:
                     print(e.output)
+                    data = {"path": os.getcwd(),
+                            "status": "FAILED",
+                            "error": "failed submission {}".format(e.output)}
 
-                response = response.decode("utf-8")
-                response = re.findall("({.+})", response, re.DOTALL)[0]
-                data = json.loads(response)
-                data.update(
-                    {
-                        "path": os.getcwd(),
-                        "status": "SUBMITTED",
-                        "start_time": datetime.utcnow(),
-                    }
-                )
                 update_dataframe_row(self.current_data, structure_id, data)
 
+
     def check_dft_calcs(self):
         """
         Helper function to check DFT calculations via polling